My new piece is an update on ivermectin for Covid-19, and why it's looking less and less likely that ivermectin works at allhttps://gidmk.medium.com/ivermectin-for-covid-19-an-update-5e913bb49483 …
-
-
That's just not true. The largest study found results that lie within the bounds of possibility of no benefit, but only just (what's the p-value, like 0.2) - the usual interpretation of such results is NOT "it doesn't work," it's "Needs more data" or "small benefit" (cont)
-
That's not true either. The CI including benefit does not make that more likely than the harm also included in the CI, and the potential harm in that study stretched up to very large amounts
- Show replies
New conversation -
-
-
Do you interpret all studies with p>0.05 as meaning that it is similarly likely that the result will be both harmful and beneficial?
-
For example if the 95% CI of a hazard ratio spanned from 0.997 to 2.59 and p>0.05?
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.